LiteRT vs TensorFlow Lite: what changed, plus the old-name new-name cheat sheet

Google's LiteRT, the renamed TensorFlow Lite, has evolved with new package names and APIs, including the CompiledModel interface and litert-torch for PyTorch conversion. The TensorFlow Lite packages are now in maintenance mode, receiving only critical updates, while LiteRT 2.2.0 offers a unified dependency for Android, Python, and PyTorch workflows.

Last verified: 2026-09-05 — LiteRT 2.2.0, LiteRT-LM 0.16.1, litert-torch 0.9.4, ai-edge-litert 2.2.0. Every version and link below was read on that date. On-device tooling moves monthly; check the linked page before you pin anything. LiteRT is TensorFlow Lite, renamed on 2024-09-04. Same .tflite file format, same models, same Interpreter API. Four things changed since then: org.tensorflow:tensorflow-lite → com.google.ai.edge.litert:litert . Python tflite-runtime → ai-edge-litert . PyTorch converter ai-edge-torch → litert-torch . CompiledModel . torch.export straight to .tflite . No ONNX step, no TensorFlow graph. TensorFlow Lite packages are in maintenance mode. The tensorflow/lite README says they "only receive critical security and stability updates". If you start today: com.google.ai.edge.litert:litert:2.2.0 with CompiledModel on Android, ai-edge-litert in Python, litert-torch for PyTorch models, LiteRT-LM for on-device LLMs. An existing TensorFlow Lite app keeps working. You can move one package at a time. | You have | Use instead | Notes | |---|---|---| | org.tensorflow:tensorflow-lite:2.17.0 | com.google.ai.edge.litert:litert:2.2.0 | Google Maven only, not Maven Central. Contains both Interpreter and CompiledModel ; minSdk 23. The 1.4.x line is Interpreter -only, minSdk 21. | | org.tensorflow:tensorflow-lite-gpu | nothing extra on 2.x; the GPU accelerator is inside litert | litert-gpu stops at 1.4.2 Interpreter API . | | org.tensorflow:tensorflow-lite-support / -metadata | com.google.ai.edge.litert:litert-support / litert-metadata 1.4.2 | No 2.x release of either. | | -select-tf-ops , -task- , -hexagon | no LiteRT-named artifact | Task Library and Model Maker stay under the TensorFlow Lite name. | | com.google.android.gms:play-services-tflite- | unchanged 16.5.0 | The Play services runtime keeps the tflite name. No code change. | | GpuDelegate / NnApiDelegate on Interpreter | CompiledModel.Options Accelerator.GPU or Accelerator.NPU | NNAPI is deprecated from Android 15 Android docs . | | Qualcomm qnn-litert-delegate + qnn-runtime | Accelerator.NPU on CompiledModel , one dependency | NPU page lists Google Tensor, Qualcomm, MediaTek, Samsung, Intel. | | You have | Use instead | Notes | |---|---|---| | pip install tflite-runtime tflite runtime.interpreter | pip install ai-edge-litert ai edge litert.interpreter.Interpreter , ai edge litert.compiled model.CompiledModel | tflite-runtime last shipped 2023-10 with wheels up to Python 3.11 and carries no deprecation note. ai-edge-litert 2.2.0 ships cp310 to cp314; its PyPI classifiers still say 3.8–3.11, ignore them. | | tf.lite.Interpreter for inference | ai-edge-litert | — | | tf.lite.TFLiteConverter TensorFlow / Keras → .tflite | unchanged | Still the converter for TensorFlow models. | | pip install ai-edge-torch ai edge torch.convert | pip install litert-torch litert torch.convert model, sample inputs | ai-edge-torch 0.7.2 is a deprecation stub that says so. litert-torch 0.9.4 is a pure-Python wheel; its native part, litert-converter 0.4.0, has cp310–cp314 wheels. Installing pulls torch, jax and transformers 2.0 GB, 93 packages on 2026-09-05 , not TensorFlow. | | — | pip install ai-edge-quantizer | Post-training quantization for LiteRT. | | — | pip install litert-lm | LiteRT-LM CLI Python ≥ 3.10 to run .litertlm bundles on a desktop. | | Area | State on 2026-09-05 | |---|---| | iOS / Swift | The official quickstart still says pod 'TensorFlowLiteSwift' 2.17.0. LiteRTSwift on CocoaPods is nightly-only and stopped in 2025-06. No LiteRT core Swift package. LiteRT-LM has one import LiteRTLM , early preview . | | Web | @tensorflow/tfjs-tflite → @litertjs/core 2.5.3 WebGPU, Wasm/XNNPack, WebNN . @litertjs/tfjs-interop bridges TF.js tensors. | | LLMs | The MediaPipe LLM Inference page says it is "in maintenance-only mode. New features and optimizations will be focused on LiteRT-LM". LiteRT-LM: com.google.ai.edge.litertlm:litertlm-android 0.16.1 litertlm-jvm for desktop , .litertlm bundles, Kotlin / Python / C++ stable, Swift / JS early preview. | | Situation | Pick | Why | |---|---|---| | New Android app, GPU or NPU with one line | CompiledModel in litert 2.x | Accelerator is an option; no delegate wiring. | | Existing TensorFlow Lite app, minSdk < 23 | litert 1.4.x Interpreter | Same API surface, minSdk 21. | | App already on Play services | keep play-services-tflite- | Officially unchanged. | | Detection / segmentation / audio with pre- and post-processing done for you | MediaPipe Tasks | Some MediaPipe models Selfie Segmenter, for one use MediaPipe-only ops such as Convolution2DTransposeBias ; they do not load in plain LiteRT. | | On-device LLM | LiteRT-LM | MediaPipe LLM Inference is maintenance-only. | | PyTorch model to Android | litert-torch → .tflite → CompiledModel | Direct torch.export path. | // build.gradle.kts — served from Google Maven, not Maven Central dependencies { implementation "com.google.ai.edge.litert:litert:2.2.0" } // keep the asset mmappable: android { androidResources { noCompress += "tflite" } } python import com.google.ai.edge.litert.Accelerator import com.google.ai.edge.litert.CompiledModel val model = CompiledModel.create context.assets, "model.tflite", CompiledModel.Options Accelerator.GPU , // NPU with GPU fallback: Options Accelerator.NPU, Accelerator.GPU null // Environment; null = default val inputs = model.createInputBuffers val outputs = model.createOutputBuffers inputs 0 .writeFloat inputArray // FloatArray in the layout you exported NCHW from litert-torch model.run inputs, outputs // enqueues on the GPU val logits = outputs 0 .readFloat // the readback is what waits // TensorBuffer and CompiledModel are AutoCloseable; close them or you leak native memory. Two rules that are easy to miss: with Accelerator.GPU , every op in the graph must be GPU-compatible there is no CPU fallback inside CompiledModel , and GPU tensors are rank 4 at most. python3.12 -m venv .venv && . .venv/bin/activate ran on 3.12.13 and 3.14.6 on 2026-09-05 pip install ai-edge-litert litert-torch pulls torch, jax, transformers; ~2 GB; no TensorFlow python import numpy as np, torch, litert torch from ai edge litert.interpreter import Interpreter x = torch.randn 1, 3, 224, 224 litert torch.convert model.eval , x, .export "model.tflite" torch.export → .tflite, nothing in between it = Interpreter model path="model.tflite" ; it.allocate tensors inp, out = it.get input details 0 , it.get output details 0 it.set tensor inp "index" , x.numpy ; it.invoke print it.get tensor out "index" Same file through CompiledModel, the API Android uses CPU here; GPU on macOS is Metal from ai edge litert.compiled model import CompiledModel from ai edge litert.hardware accelerator import HardwareAccelerator cm = CompiledModel.from file "model.tflite", HardwareAccelerator.CPU ins, outs = cm.create input buffers 0 , cm.create output buffers 0 ins 0 .write x.numpy ; cm.run by index 0, ins, outs print outs 0 .read 10, np.float32 Run on 2026-09-05 with a conv + nn.MultiheadAttention model: conversion took 1–2 s, outputs were within 7e-7 of PyTorch, identical results on Python 3.12 and 3.14. Use it when you deploy .tflite models on Android with GPU or NPU, when you want a torch.export -based converter, or when you need a Google-maintained LLM runtime with NPU backends. Do not pick it for an iOS-only app today. The iOS path is still the TensorFlow Lite pod, and Core ML, MLX and llama.cpp have more direct iOS routes. For arbitrary Hugging Face LLMs on a Mac, GGUF with llama.cpp or MLX needs no conversion step; LiteRT-LM needs a .litertlm bundle Hugging Face litert-community has 343 models on 2026-09-05, many ungated, Qwen2.5-1.5B-Instruct among them . ExecuTorch PyTorch's own runtime, torch.export → .pte , ONNX Runtime Mobile Maven AAR, NNAPI / XNNPACK / QNN providers , llama.cpp GGUF, Metal / Vulkan / CPU , MLX Apple Silicon . All four are reasonable defaults. This page is about what LiteRT calls things, not a ranking. pip install tflite-runtime . litert:2.1.0 next to a table that lists 2.2.0 as latest. /edge/litert/next/ . Blogs say LiteRT; the version-bearing statement is the GitHub v2.1.0 note "beta… officially recommending that developers begin their transition" . mediapipe/util/tflite/operations/ and issues. .task and .litertlm . Is TensorFlow Lite deprecated? Maintenance mode: "only receive critical security and stability updates. All active on-device ML development… transitioned to LiteRT" tensorflow/lite README . Do my .tflite files still work? Yes. Format and extension are unchanged. Does LiteRT run on iOS? Through the TensorFlow Lite pod for now. LiteRT-LM has a Swift package in early preview. Where are ready-made models? Hugging Face litert-community 343 models, .tflite and .litertlm and Kaggle Models the filter is still named tfLite .